Related papers: Joint Sound Source Separation and Speaker Recognit…
Automatic meeting analysis comprises the tasks of speaker counting, speaker diarization, and the separation of overlapped speech, followed by automatic speech recognition. This all has to be carried out on arbitrarily long sessions and,…
Most approaches to multi-talker overlapped speech separation and recognition assume that the number of simultaneously active speakers is given, but in realistic situations, it is typically unknown. To cope with this, we extend an iterative…
Collaborative filtering generates recommendations by exploiting user-item similarities based on rating data, which often contains numerous unrated items. To predict scores for unrated items, matrix factorization techniques such as…
We propose a method for noise reduction, the task of producing a clean audio signal from a recording corrupted by additive noise. Many common approaches to this problem are based upon applying non-negative matrix factorization to…
Nonnegative matrix factorization (NMF) is a powerful technique for dimension reduction, extracting latent factors and learning part-based representation. For large datasets, NMF performance depends on some major issues: fast algorithms,…
Single-channel speech separation is a crucial task for enhancing speech recognition systems in multi-speaker environments. This paper investigates the robustness of state-of-the-art Neural Network models in scenarios where the pitch…
In this paper, a novel architecture for speaker recognition is proposed by cascading speech enhancement and speaker processing. Its aim is to improve speaker recognition performance when speech signals are corrupted by noise. Instead of…
Multi-channel speech separation using speaker's directional information has demonstrated significant gains over blind speech separation. However, it has two limitations. First, substantial performance degradation is observed when the coming…
The mid-infrared (MIR) spectra observed with the \textit{Spitzer} Infrared Spectrograph (IRS) provide a valuable dataset for untangling the physical processes and conditions within galaxies. This paper presents the first attempt to blindly…
Semi-Non-negative Matrix Factorization is a technique that learns a low-dimensional representation of a dataset that lends itself to a clustering interpretation. It is possible that the mapping between this new representation and our…
Deep neural network models for speech recognition have achieved great success recently, but they can learn incorrect associations between the target and nuisance factors of speech (e.g., speaker identities, background noise, etc.), which…
Symmetric nonnegative matrix factorization (NMF), a special but important class of the general NMF, is demonstrated to be useful for data analysis and in particular for various clustering tasks. Unfortunately, designing fast algorithms for…
Recently, deep neural network (DNN) based time-frequency (T-F) mask estimation has shown remarkable effectiveness for speech enhancement. Typically, a single T-F mask is first estimated based on DNN and then used to mask the spectrogram of…
NMR spectral datasets, especially in systems with limited samples, can be difficult to interpret if they contain multiple chemical components (phases, polymorphs, molecules, crystals, glasses, etc...) and the possibility of overlapping…
Nonnegative matrix factorization (NMF) is a popular data embedding technique. Given a nonnegative data matrix $X$, it aims at finding two lower dimensional matrices, $W$ and $H$, such that $X\approx WH$, where the factors $W$ and $H$ are…
Non-negative matrix factorization (NMF) is widely used for dimensionality reduction and interpretable analysis, but standard formulations are unsupervised and cannot directly exploit class labels. Existing supervised or semi-supervised…
Dimensionality reduction is considered as an important step for ensuring competitive performance in unsupervised learning such as anomaly detection. Non-negative matrix factorization (NMF) is a popular and widely used method to accomplish…
We introduce negative binomial matrix factorization (NBMF), a matrix factorization technique specially designed for analyzing over-dispersed count data. It can be viewed as an extension of Poisson matrix factorization (PF) perturbed by a…
Speech recognition system performance degrades in noisy environments. If the acoustic models are built using features of clean utterances, the features of a noisy test utterance would be acoustically mismatched with the trained model. This…
This work presents a novel framework based on feed-forward neural network for text-independent speaker classification and verification, two related systems of speaker recognition. With optimized features and model training, it achieves 100%…